code-search-selector

A guide for choosing between semantic code search and ordinary text or file search. Semantic search looks for related code by meaning, while ordinary search finds exact text or file patterns.

In plain words
What is it for?
Use it when investigating how code works, finding implementations, mapping architecture, tracing data flow, auditing integrations, or locating exact symbols and files.
Why use it?
It helps select an appropriate search method, reducing unnecessary file reading for broad codebase questions and avoiding semantic tools for simple exact matches.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/madappgang/claude-code/code-search-selector
Any agent
npx skills add MadAppGang/claude-code --skill code-search-selector
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.02438
Opus 5 $0.00031 $0.01219
Sonnet 5 $0.00012 $0.00488
Haiku 4.5 $0.00006 $0.00244

Measured 2d ago against content hash dfc851eae1ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-search-selector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/code-analysis/skills/code-search-selector/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Search Tool Selector

This skill helps choose the most effective search tool for your task.

When Semantic Search Works Better

Claudemem provides better results for conceptual queries:

Query Type Example Recommended Tool
"How does X work?" "How does authentication work?" claudemem search
Find implementations "Find all API endpoints" claudemem search
Architecture questions "Map the service layer" claudemem --agent map
Trace data flow "How does user data flow?" claudemem search
Audit integrations "Audit Prime API usage" claudemem search

When Native Tools Work Better

Query Type Example Recommended Tool
Exact string match "Find 'DEPRECATED_FLAG'" Grep
Count occurrences "How many TODO comments?" Grep -c
Specific symbol "Find class UserService" Grep
File patterns "Find all *.config.ts" Glob

Why Semantic Search is Often More Efficient

Token Efficiency: Reading 5 files costs ~5000 tokens; claudemem search costs ~500 tokens with ranked results.

Context Discovery: Claudemem finds related code you didn't know to ask for.

Ranking: Results sorted by relevance and PageRank, so important code comes first.

Example: Semantic Query

User asks: "How does authentication work?"

Less effective approach:

grep -r "auth" src/
# Result: 500 lines of noise, hard to understand

More effective approach:

claudemem status  # Check if indexed
claudemem search "authentication login flow JWT"
# Result: Top 10 semantically relevant code chunks, ranked

Quick Decision Guide

Classify the Task

User Request Category Recommended Tool
"Find all X", "How does X work" Semantic claudemem search
"Audit X integration", "Map data flow" Semantic claudemem search
"Understand architecture", "Trace X" Semantic claudemem map
"Find exact string 'foo'" Exact Match Grep
"Count occurrences of X" Exact Match Grep
"Find symbol UserService" Exact Match Grep

Read the full file on GitHub · 303 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 303 lines · 62 tokens per session scan A dfc851eae1ed

Subscribe to this mod's changes

code-search-selector is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 2,438 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens